OptiHive: Ensemble Selection for LLM-Based Optimization via Statistical Modeling
This addresses the problem of unreliable and slow LLM-based optimization for users needing automated problem-solving, representing a strong specific gain rather than a broad paradigm shift.
The paper tackles the unreliability and latency of LLM-based optimization solvers by introducing OptiHive, a framework that enhances solver-generation pipelines to produce higher-quality solvers from natural-language descriptions, resulting in an increase in optimality rate from 5% to 92% on complex problems.
LLM-based solvers have emerged as a promising means of automating problem modeling and solving. However, they remain unreliable and often depend on iterative repair loops that result in significant latency. We introduce OptiHive, a framework that enhances any solver-generation pipeline to produce higher-quality solvers from natural-language descriptions of optimization problems. OptiHive uses a single batched generation to produce diverse components (solvers, problem instances, and validation tests) and filters out erroneous components to ensure fully interpretable outputs. Accounting for the imperfection of the generated components, we employ a statistical model to infer their true performance, enabling principled uncertainty quantification and solver selection. On tasks ranging from traditional optimization problems to challenging variants of the Multi-Depot Vehicle Routing Problem, OptiHive significantly outperforms baselines, increasing the optimality rate from 5% to 92% on the most complex problems.